© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143774
    Prev
    Next
    INDEX
    Explanations

    see what

    np_acts-logits-general · gemini-2.5-flash-lite

    situation or key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéal
    0.50
    ⵙ
    0.48
    すが
    0.47
    生地
    0.47
    TypeScript
    0.47
     pana
    0.46
     matériel
    0.46
    栽培
    0.45
    사진
    0.45
    写真
    0.45
    POSITIVE LOGITS
     kork
    0.51
     Newell
    0.48
     Grizz
    0.47
     i
    0.46
     newInput
    0.46
    ken
    0.46
     Hemingway
    0.46
     Hatfield
    0.46
     Haaland
    0.46
     className
    0.45
    Activations Density 0.001%

    No Known Activations